Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ndisisnd/msg/mergenpx skills add ndisisnd/msg --skill mergegit clone --depth 1 https://github.com/ndisisnd/msgWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00094 | $0.01983 |
| Opus 5 | $0.00047 | $0.00992 |
| Sonnet 5 | $0.00019 | $0.00397 |
| Haiku 4.5 | $0.00009 | $0.00198 |
Grade A, and why
merge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
merge
The ship gate. Runs after /pre-merge opened a feature→staging PR and takes it the
rest of the way: onto staging (tested by a human), then onto main (production,
double-confirmed). It is the only skill in the harness that merges — eng commits to
feature branches, pre-merge opens PRs. Nothing reaches main any other way.
pre-merge (PR feature→staging) → merge --staging → (human tests staging) → merge --production → (double-confirm) → PR staging→main → main (live)
Usage
/merge --staging [--prd <path>]— merge the feature→staging PR on green CI, deploy + verify staging, emit a human test script, stamp the sign-off on approval (refs/staging.md);--prdnames the shipped PRD explicitly (else resolved from the PR head branchfeat/prd-<n>-*)/merge --production [--prd <path>]...— the double-confirmed release: PR toprod, merge, deploy, verify, tag (refs/production.md);--prd(repeatable) names the PRD(s) this release ships — the release body + the sign-off precondition/merge --production [--bump <major|minor|patch>] [--version <x.y.z>]— override the release version (default: minor bump from the lastv*tag on prod); the resolvedv<x.y.z>+<build>is shown in the confirm (refs/release-identity.md)/merge --init— detect ship tooling, interview about the gaps, writedevkit/policy.json; performs no merge, PR, or deploy (refs/protocol-init.md)/merge --quiet/--status <n>m— suppress or retune this run's status heartbeat; flag beats policy beats default (../shared/refs/status-heartbeat.md)
Natural language: "ship this to staging", "merge the staging PR", "promote to production", "release to production", "ship it live".
Posture
Release manager on a small product team. Owns the two irreversible-ish moments — the
staging merge and the production release. Compact and checklist-driven. Ship gates
never collapse: the green-CI check, the human test, and the production
double-confirmation run in every invocation. Under release_flow=direct the staging
stage is inactive — not waived; its human judgment moves to the inline human-test
approval, before the merge (../shared/refs/policy-schema-merge.md §1b).
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- refs/deploy.md 4.7 KB
- refs/failed-ship.md 3.7 KB
- refs/human-test-script.md 3.9 KB
- refs/output-schema.md 13 KB
- refs/production.md 32 KB
- refs/protection.md 3.3 KB
- refs/protocol-init.md 16 KB
- refs/refusal-patterns.md 11 KB
- refs/release-identity.md 7.7 KB
- refs/sanctioned-writes.md 2.2 KB
- refs/staging.md 18 KB
- refs/submission.md 10 KB
- refs/verify-deploy.md 18 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 101 lines · 94 tokens per session scan A cc2f12d81301
merge is a skill published in the GitHub repository ndisisnd/msg (6 stars, last pushed 16d ago), licensed MIT. It adds 94 tokens to every session and 1,983 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
release-check
Pre-release checklist for Forge — verify, version bump, changelog, docs, docker build, smoke test. Run before tagging v.
landing
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
skillspec-migrate
Complete a .agent.partial file by resolving TODO markers.
skill-writer
Review a SkillSpec .agent file for quality, correctness, and adherence to SkillSpec design principles.
skillspec-backport
Reconcile changes from a modified SKILL.md back into the .agent source file.